Advanced AI Full Stack Engineer
accentureArlington (VA)
Advanced AI Full Stack Engineer
Posted today
accentureArlington (VA)
SENIORITY
Lead
About the role
Overview:
In this role you design and build foundational AI agent platforms, spanning orchestration runtimes, sandboxed environments, and developer tooling. You work across the full stack, shaping how agents operate in enterprise settings with an emphasis on governance, observability, and scalable delivery. You partner with researchers, PMs, security engineers, and architects to translate complex AI use cases into robust platform capabilities. This is an onsite, Mountain View-based opportunity with travel as needed. Compensation / Benefits medical, dental, vision, life, and long-term disability coverage 401(k) plan bonus opportunities paid holidays paid time off
Responsibilities:
Design and build agent orchestration runtimes and stateful execution loops Create sandboxed execution environments with declarative policy enforcement Develop pluggable provider interfaces for sandbox backends Build Python/Node.js/TypeScript SDKs and CLIs for developers Design REST, gRPC, WebSocket, and SSE APIs for agent runtimes and platform services Implement framework adapters to unify event streams from AI frameworks Develop intelligent inference routing layers based on data sovereignty and cost Design memory architectures including vector databases and cross-session stores Implement ephemeral credential injection and RBAC-limited data access Instrument components with OpenTelemetry and collect latency metrics Build CI/CD governance tooling with schema validation and regulatory controls Enable human-in-the-loop approval gates and audit trails Collaborate with AI researchers, product managers, security engineers, and enterprise architects
Key requirements:
Bachelor's degree in Computer Science, Computer Engineering, or related field or equivalent 2+ years of Python and/or Node.js/TypeScript building production backend services or platform tooling 1+ year of experience with AI/LLM systems, agent frameworks, or AI developer tooling experience with async Python frameworks (FastAPI, asyncio) and containerization/Kubernetes familiarity with event-streaming protocols (WebSocket, SSE, gRPC) experience with vector/relational databases and framework ecosystems (LangGraph, OpenAI Agents SDK, Anthropic Claude SDK) cross-functional collaboration technical leadership clear communication of architectural trade-offs Python Node.js/TypeScript FastAPI
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.